论文标题
具有可区分动态编程的深度学习网络，用于视网膜OCT表面细分
A deep learning network with differentiable dynamic programming for retina OCT surface segmentation
论文作者
论文摘要
光学相干断层扫描（OCT）图像中的多表面分割是一个挑战问题，由于频繁存在弱图像边界而使其复杂化。最近，为此任务开发了许多基于深度学习（DL）的方法，并产生出色的性能。不幸的是，由于医学成像中训练数据的稀缺性，DL网络学习目标表面的全球结构（包括表面平滑度）是一项挑战。为了弥合这一差距，本研究建议通过有限的可区分动态编程模块无缝统一特征学习的U-NET，以实现视网膜OCT表面分割的端到端学习，以明确执行表面平滑度。它有效地利用了下游模型优化模块的反馈来指导特征学习，从而更好地执行目标表面的全球结构。对视网膜层分割的Duke AMD（与年龄相关的黄斑变性）和JHU MS（多发性硬化症）OCT数据集进行的实验表明非常有希望的分割精度。
Multiple-surface segmentation in Optical Coherence Tomography (OCT) images is a challenge problem, further complicated by the frequent presence of weak image boundaries. Recently, many deep learning (DL) based methods have been developed for this task and yield remarkable performance. Unfortunately, due to the scarcity of training data in medical imaging, it is challenging for DL networks to learn the global structure of the target surfaces, including surface smoothness. To bridge this gap, this study proposes to seamlessly unify a U-Net for feature learning with a constrained differentiable dynamic programming module to achieve an end-to-end learning for retina OCT surface segmentation to explicitly enforce surface smoothness. It effectively utilizes the feedback from the downstream model optimization module to guide feature learning, yielding a better enforcement of global structures of the target surfaces. Experiments on Duke AMD (age-related macular degeneration) and JHU MS (multiple sclerosis) OCT datasets for retinal layer segmentation demonstrated very promising segmentation accuracy.
